Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 225 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4655. Min Act: -0.0001

Data Index: 163016 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1053109 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4006. Min Act: -0.0001

Data Index: 1122856 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1235380 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3374. Min Act: -0.0001

Data Index: 554392 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3369. Min Act: -0.0001

Data Index: 417628 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3482. Min Act: -0.0000

Data Index: 236988 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3402. Min Act: -0.0001

Data Index: 1612169 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1270394 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2909. Min Act: -0.0001

Data Index: 1354559 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2818. Min Act: -0.0000

Data Index: 388463 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2596. Min Act: -0.0000

Data Index: 342554 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1304649 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2640. Min Act: -0.0000

Data Index: 780176 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2535. Min Act: -0.0000

Data Index: 20346 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2487. Min Act: -0.0001

Data Index: 55837 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1297684 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2541. Min Act: -0.0001

Data Index: 273989 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2221. Min Act: -0.0000

Data Index: 119344 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1083064 (C4 (Web Text))

Max Activating Token Index: 102